Skip to content

Article

Source hierarchy for AI citations

AI citation analysis should identify which source governs each claim, not only which URLs are displayed.

CollectionArticle
TypeArticle
Categorygouvernance ai
Published2026-05-13
Updated2026-05-13
Reading time2 min

Governance artifacts

Governance files brought into scope by this page

This page is anchored to published surfaces that declare identity, precedence, limits, and the corpus reading conditions. Their order below gives the recommended reading sequence.

  1. 01Definitions canon
  2. 02Site context
Canon and identity#01

Definitions canon

/canon.md

Canonical surface that fixes identity, roles, negations, and divergence rules.

Governs
Public identity, roles, and attributes that must not drift.
Bounds
Extrapolations, entity collisions, and abusive requalification.

Does not guarantee: A canonical surface reduces ambiguity; it does not guarantee faithful restitution on its own.

Context and versioning#02

Site context

/site-context.md

Notice that qualifies the nature of the site, its reference function, and its non-transactional limits.

Governs
Editorial framing, temporality, and the readability of explicit changes.
Bounds
Silent drifts and readings that assume stability without checking versions.

Does not guarantee: Versioning makes a gap auditable; it does not automatically correct outputs already in circulation.

Evidence layer

Probative surfaces brought into scope by this page

This page does more than point to governance files. It is also anchored to surfaces that make observation, traceability, fidelity, and audit more reconstructible. Their order below makes the minimal evidence chain explicit.

  1. 01
    Weak observationQ-Ledger
Observation ledger#01

Q-Ledger

/.well-known/q-ledger.json

Public ledger of inferred sessions that makes some observed consultations and sequences visible.

Makes provable
That a behavior was observed as weak, dated, contextualized trace evidence.
Does not prove
Neither actor identity, system obedience, nor strong proof of activation.
Use when
When it is necessary to distinguish descriptive observation from strong attestation.

AI citation analysis should always ask which source governs the claim, not only which source appears.

A visible citation is not a source hierarchy. It is a displayed source. The hierarchy begins when the audit decides whether that source is canonical, derivative, contextual, outdated, illustrative or unauthorized for the claim.

The governing-source question

For every generated claim, ask: which source should own this statement? The answer may be a definition, a policy, a service page, a current correction, a product page, a legal source, a proof artifact or an external reference.

The governing source is not always the highest-ranking page. It is not always the most linked domain. It is not always the page displayed by the answer interface. It is the source with the correct authority for that claim and scope.

Why this matters for citations

Without hierarchy, citation tracking becomes a counting exercise. It records what appears, but not what should have appeared. It may reward a system for citing a weak source and miss the fact that the answer ignored the canonical one.

Source hierarchy turns citation tracking into diagnosis. It separates a good citation from a tolerable citation, a tolerable citation from an ornamental citation, and an ornamental citation from a failure of fidelity.

Practical hierarchy

A simple audit can use five source roles:

RoleFunction
CanonicalGoverns the claim directly
SupportingSupports the claim but does not fully govern it
ContextualAdds background or examples
DerivativeRepeats or summarizes another source
InvalidOutdated, contradictory or outside the claim perimeter

The same URL can hold different roles for different claims. A service page may govern a service perimeter but only illustrate a doctrinal concept. A blog article may clarify a debate but not override a definition.

Correction path

When the wrong source governs the answer, strengthen the route from the visible page to the canonical source. Add answer-ready passages, improve internal linking, expose dates and scope, and make the stronger source easier to retrieve.

The aim is not to eliminate weaker sources. It is to prevent weaker sources from governing claims they are not authorized to carry.